Three-dimensional medical image analysis method and system for identification of vertebral fractures

Abstract

A machine-based learning method estimates a probability of bone fractures in a 3D image, more specifically vertebral fractures. The method and system utilizing such method utilize a data-driven computational model to learn 3D image features for classifying vertebra fractures. A three-dimensional medical image analysis system for predicting a presence of a vertebral fracture in a subject includes a 3D image processor for receiving and processing 3D image data of a 3D image of the subject, producing two or more sets of 3D voxels. Each of the sets of 3D voxels corresponds to an entirety of the 3D image and each of the sets of 3D voxels consists of equal 3D voxels of different dimensions. The system also includes a voxel classifier for assigning the 3D voxels one or more class probabilities each of the 3D voxels contains a fracture using a computational model, and a fracture probability estimator for estimating a probability of the presence of a vertebral fracture in the subject.

Description

[0001]The present disclosure relates to medical image analysis and provides a system and a method for identification of bone fractures in 3D images, more specifically vertebral fractures.BACKGROUND[0002]Osteoporosis is a disease affecting bones where increased bone weakness increases the risk of bone fractures. Common osteoporotic fractures occur in the vertebrae in the spine, the bones of the forearm, and the hip. Every 3 seconds an osteoporotic fracture occurs, with vertebral fractures being the most common (Johnell et al, 2006). Vertebral fractures are predictive of subsequent fractures, e.g. patients with moderate or severe vertebral fractures have 4.8 to 6.7 times higher risk of subsequent hip fracture (Buckens et al., 2014). Roux et al demonstrated that 1 out of 4 patients with incident mild vertebral fractures will most probably have a fracture again within subsequent 2 years (Roux et al., 2007).[0003]Clinical assessment of vertebral fractures is difficult because many patien...

AI Technical Summary

Benefits of technology

The present patent is about a system and method for analyzing 3D images of a person's spinal cord to predict if they have a vertebral fracture. The system includes a processor that receives and processes image data, creating sets of voxels that contain equal amounts of data at different dimensions. The system then uses a computational model to assign each voxel a probability of containing a fracture. The method involves identifying specific voxels that are classified as containing a fracture and predicting the presence of a vertebral fracture based on this identification. Overall, this system and method can help healthcare professionals quickly and accurately detect spinal fractures, potentially improving patient outcomes.

Problems solved by technology

Clinical assessment of vertebral fractures is difficult because many patients are unaware that they have suffered a vertebral fracture.

Despite efforts from the International Osteoporosis Foundation to raise awareness of vertebral fractures and provide training on vertebra fracture detection, bone care givers in clinical centers have little means for screening and early-stage diagnosis of patients with vertebral fractures.

As clinical imaging data volumes keep growing steadily, developing a three-dimensional image processing system and a method is a technical problem of great clinical importance to reduce inter-observer variability and to allow for screening for vertebral fractures.

Images